Backend: AI generation endpoints (Gemini nano-banana + Veo)

Server-side proxy so the Google API key (from Infisical) never reaches the
client. Behind an AiClient trait with a fake for headless tests.

- ai.rs: GeminiClient — refine prompt (gemini-2.5-flash), generate image
  (gemini-2.5-flash-image / "nano-banana"), and async video (veo-2.0:
  predictLongRunning → poll → proxy the redirecting download). DisabledAiClient
  when no key is configured.
- POST /v1/ai/refine, /v1/ai/image (rate-limited 60/h, 20/h)
- POST /v1/ai/video (submit, 5/h) + /v1/ai/video/status (poll → base64 mp4)
- config: GEMINI_API_KEY via SecretSource
- 5 endpoint/parse tests; full workspace gate green (114 tests)

Live-verified: refine + nano-banana return through the proxy; Veo submits,
polls to done in ~60s, and streams back a valid mp4.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
This commit is contained in:
Omar Sobh
2026-06-05 12:56:19 -05:00
co-authored by Claude Opus 4.8
parent eddca62f23
commit 4be1cf5fa3
10 changed files with 597 additions and 1 deletions
@@ -18,6 +18,7 @@ use http_body_util::BodyExt;
use serde_json::Value;
use tower::ServiceExt;
use cardclaws_api::ai::FakeAiClient;
use cardclaws_api::assets::InMemoryStore;
use cardclaws_api::cache::InMemoryCache;
use cardclaws_api::email::CapturingEmailSender;
@@ -84,6 +85,7 @@ pub async fn try_setup() -> Option<TestApp> {
email: email.clone(),
assets: assets.clone(),
geo: Arc::new(FakeGeo),
ai: Arc::new(FakeAiClient),
jwt: JwtKeys::new("test-jwt-secret"),
apple: Arc::new(NoopApple),
apple_audience: "com.cardclaws.test".into(),